• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5C
• /
• pp.478-486
• /
• 2007

Double-talk detection errors can result in either large residual echo or distorting the near-end talker's input speech. Thus accurate double-talk detection is an important problem in the acoustic echo canceller to improve the speech quality. In the double-talk detection algorithm using a cross-correlation coefficient, double-talk detection errors can occur in the initial convergence period of an adaptive filter or in noisy environment since the cross-correlation coefficient becomes large in such situations. In this paper, we propose a new double-talk detection algorithm based on the cross-correlation method using a normalized error signal power to reduce the double-talk detection errors. The experimental results have shown the performance improvement of an acoustic echo canceller as well as the noise-robustness of the proposed double-talk detector.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.628-633
• /
• 2014

This paper proposes a performance improvement method of the conventional double talk detection method which can operate before convergence of the echo canceller. The proposed method estimates the coefficients of the linear predictive coding(LPC) filter by using the primary input signal. The time-varying threshold for double talk detection is determined based on the LPC filter gain of the primary input signal level. The proposed method can reduce not only false detection rate which means wrong detection of single talk as double talk but also double talk detection delay. Computer simulation was performed using a long-term real speech signals. It is shown that the proposed method improves the conventional method in terms of lowering the false detection rate and shortening the detection delay.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.4
• /
• pp.401-407
• /
• 2009

In this paper, we propose a novel method for the cross-correlation based double-talk detection (DTD), which employing the Gaussian Mixture Model (GMM) in the frequency domain. The proposed algorithm transforms the cross correlation coefficient used in the time domain into 16 channels in the frequency domain using the discrete fourier transform (DFT). The channels are then selected into seven feature vectors for GMM and we identify three different regions such as far-end, double-talk and near-end speech using the likelihood comparison based on those feature vectors. The presented DTD algorithm detects efficiently the double-talk regions without Voice Activity Detector which has been used in conventional cross correlation based double-talk detection. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional schemes. especially, show the robustness against detection errors resulting from the background noises or echo path change which one of the key issues in practical DTD.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.7
• /
• pp.34-41
• /
• 2000

This paper proposes a new double-talk detection algorithm which is based on the fuzzy rules, in the adaptive echo canceller of telecommunication system. In this method, the two inputs of the fuzzy inference for detecting double-talk condition are used. One is the cross-correlation coefficient between the error signal and the primary signal which is the summation of the real echo signal and the near-end signal. The other one is the cross-correlation coefficient between the estimation error signal and the primary signal. The fuzzy controller makes a fuzzification for two inputs by the membership functions of trapezoid does the max-min composition using if-then rules. The composed result is defuzzificated by the center gravity method. And by defuzzificated values, the double-talt the echo path variance, and the echo path variance during the double-talk are detected. It is confirmed by computer simulation that this fuzzy double-talk detector is able to estimate the double talk and the echo path variation condition, and even track echo path variation more accurately than the conventional algorithm during the double-talk period.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.10
• /
• pp.141-150
• /
• 1997

In this paepr, we propose an intelligent double talk detector that can enhance the performance of the acoustic echo cancellation system. The conventional double talk detection methods often misunderstand the echo path changes as double talk. Although there exist several detection methods that can distinguish the echo path changes from the double-talks, they show poor tracking performance because of the excessive decision delay for the discrimination and can only be used after the adaptive digital filter converges. A new and more effective ditetion algorithm has been proposed, where the detection mechanism is performed by observing the change rate of the reflection coefficients of the two lattice predictors that re placed on the near-end and far-end terminals. The excellence of the proposed method is verified by extensive computer simulations using real speech signals.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.3
• /
• pp.285-289
• /
• 2009

In this paper, we propose a novel double-talk detection (DTD) technique based on soft decision in the frequency domain. In the proposed method, global near-end speech presence probability (GNSPP) considering the statistical model assumption and voice activity detection (VAD) decision of the near-end and far-end signal are applied to the DTD algorithm in the frequency domain instead of the traditional hard decision scheme using cross-correlation coefficients. The performance of the proposed algorithm is evaluated by the objective test under various environments, and yields better results compared with the conventional scheme.

• Journal of Korea Multimedia Society
• /
• v.11 no.3
• /
• pp.281-291
• /
• 2008

In this paper, we propose a new double talk detection algorithm which detects near end signals with less degradation, tracking echo path variation of echo canceler simultaneously. Our method makes use of a cross-correlation between channel input signals and estimated error signals and a normalized cross-correlation between microphone input signals and estimated error signals. By combing thresholds for these cross-correlations pertinently, this algorithm discriminates between variation of echo path and occurrence of double talk. These two cross-correlation are used to detect double talk periods, tracking echo path variation. During the detection period, adjustive adaptive filter is ceased to prevent the echo canceler from being disturbed by near end signals. Also, the echo canceler will still be kept on for tracking any variation in echo path. Through computer simulation results, it was confirmed that the proposed algorithm shows better performance, tracking echo path variation and detecting the double talk periods, than the Ye et. al's and the NLMS algorithms from ERLE viewpoint.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2362-2367
• /
• 2005

This paper reports a technique for discriminating double talk and echo path change using the stochastic characteristics of power change for an adaptive noise canceller. The causes of rapid error increasing are double talk and echo path change. When the echo path is changed, the system corrects the impulse response in order to reduce the error. However, in the case of double talk, the system has to suspend the updating impulse response in order to maintain the quality of the voice signal. In the conventional system, it was difficult to discriminate between the two situations. In this research, the stochastic characteristics of the voice power change in the double talk period were experimentally verified to be different from the power change during echo path changing. Based on the results, a new double talk detection method is proposed.

• The Journal of the Acoustical Society of Korea
• /
• v.31 no.3
• /
• pp.161-169
• /
• 2012

This paper presents a robust speech end-point detector using double talk detection in echoic conditioned speech recognition robot. The proposed method consists of combining conventional end-point detector result and double talk detector result. We have tested the proposed method in isolated word recognition system under echoic conditioned environment. As a result, the proposed algorithm shows superior performance of 30 % to the available techniques in the points of speech recognition rates.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.5
• /
• pp.203-208
• /
• 2013

In this paper, we proposed a performance improvement method of the double talk detector which can operate before the echo canceller converges. Microphone input signal is filtered by the linear prediction filter and this filtered signal is used for detection. The coefficients of the linear prediction filter are given by the far-end talker signal. During single talk, filtered signal has low power since the characteristics of the echo signal is similar with those of the far-end talker signal. But, during double talk, the filtered signal does not have low power because the signal of different characteristics is included in the microphone signal. Double talk is detected by this difference. Simulations using real speech signals verified that the proposed method outperformed the conventional methods.